AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation

Boyuan Xiao, Bohong Chen, Yumeng Li, Ji Feng, Yao-Xiang Ding, Kun Zhou

ICML 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the two-stage focus plan (SceneDiver) to the VLMQwen2.5-VL-7B · Robot manipulation (MuJoCo)success rate %: 14.7 -> 28.7Improved
add SceneDiver focusgemini-2.5-flash · Robot manipulation (MuJoCo)success rate %: 38.7 -> 46.7Improved
add SceneDiver focusQwen2.5-VL-7B · Room navigation (Base)success rate %: 32.7 -> 44.0Improved
add SoM visual prompting instead of SceneDiverQwen2.5-VL-7B · Room navigation (Base)success rate %: 32.7 -> 30.0No clear effect
add extended thinking mode to the VLMgemini-2.5-flash · Room navigation (Base)success rate %: 68.0 -> 70.0No clear effect
add SceneDiver adapter to OpenVLA-OFTOpenVLA-OFT · LIBERO-plus Robot Initial States (Spatial)success rate %: 19.91 -> 29.49Improved
add SceneDiver adapter to OpenVLA-OFTOpenVLA-OFT · LIBERO-plus Long, Light Conditionssuccess rate %: 84.47 -> 92.42Improved
add SceneDiver adapter to OpenVLA-OFTOpenVLA-OFT · LIBERO-plus Object, Objects Layoutsuccess rate %: 76.01 -> 76.82No clear effect
add coarse-to-fine focus planning instead of scene graph as text only (ablation)SceneDiver · Room navigation (Base)success rate %: 30.7 -> 44.0Improved
add step-by-step coarse-to-fine planning instead of direct focus (ablation)SceneDiver · Room navigation (Base)success rate %: 34.0 -> 44.0Improved
add fine-grained verification stage to coarse planning (ablation)SceneDiver · Room navigation (Base)success rate %: 37.3 -> 44.0Improved
drop 10% to 50% of scene graph nodes (ablation)SceneDiver · Room navigation stress testrecovery rate: 96.78 -> 97.69No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy